Anemia is a common blood disorder characterized by a deficiency of red blood cells (RBCs) or haemoglobin, reducing oxygen transport in the body. Traditional diagnostic methods, such as complete blood count (CBC) tests, are time-consuming, require laboratory facilities, and may not be accessible in remote areas. Previous studies have explored automated anemia detection using image processing and machine learning, but they often lack high accuracy or require complex hardware. This project proposes a deep learning-based approach using Convolutional Neural Networks (CNNs) to analyze eye conjunctiva images for anemia detection. The system consists of image loading, model building, model training, model evaluation and making prediction with the model modules. The expected outcome is a CNN model with high accuracy (>95%). Model that offers a fast, cost-effective, and non-invasive method for early anemia detection. Future improvements may include integrating with mobile applications, building a region-of-interest extractor that can recognize the parable conjunctiva part of the eye.